iiinova — where your digital self keeps evolving

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 07/06/2026

New Dev Notes goes out tomorrow morning. One honest take a week on building with AI, what I'm actually learning at work, and a tool worth your time. No hype. Subscribe and it lands at 8:45 ET chrisgmyr.dev/newsletter

chrisgmyr.dev

Dev Notes Newsletter - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

111

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 05/06/2026

Watching how people use #Claude / #ai, the biggest split isn't prompt skill. It's context hygiene. Some clear and re-orient between tasks. Others run one session for days and wonder why it drifts. Knowing when to clear is the skill nobody teaches. How often do you actually clear?

121

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 04/06/2026

Most mornings now I walk the neighborhood before work. Watch on, then I don't look at it. No phone, no headphones, no podcast. Just early sun and steps. My whole day moves fast with #AI. This is the part I keep slow 🌅

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 03/06/2026

The #AI PR reviewer isn't something you install and forget. It's a prompt you tune. My first version missed findings a second reviewer caught cold. The fix wasn't a smarter model. It was recalibrating the prompt. The calibration is the actual product.

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 02/06/2026

The useful #AI cost number isn't per-engineer or per-team. It's per-task. The same kind of ticket costing $1.50 one time and $15 the next isn't a billing detail. It's a map of where your workflow is inconsistent. Cost variance shows you which process to standardize next 💡

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 01/06/2026

Everyone has access to the best model now. That stopped being the edge. The teams that win the next year are the ones who stayed sharp enough to tell working from right, instead of approving a diff they never actually read. #ai #engineering New Dev Notes 👇 chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: June 1, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 27/05/2026

#AI accelerates the typing. It also accelerates the cost of not paying attention. Read the diff line by line. Note what surprised you. The small in-flight moments are where learning lives. Operator capability matters as much as agent capability right now.

031

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 26/05/2026

Code review isn't the bottleneck. Lack of judgment is. #AI generates working code in seconds. The slow part is whether anyone can tell working from right. Review is the judgment layer. It always was. AI just made the bug-catching part cheaper, so the judgment part is what's left.

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 25/05/2026

Picking up yesterday's work used to take ten minutes. With the right session log it takes ten seconds. The skill isn't clever. The friction is just gone. That changed how I work more than any model upgrade in six months. New Dev Notes 👇 chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: May 25, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

011

Slightly Caffeinated Podcast @slightlycaffeinated.fm · 23/05/2026

🎙️ Just published a new episode of Slightly Caffeinated: Turkish Coffee Finally, Multi-Step Synthesis, and AI as Enhancement. Have a listen:

share.transistor.fm

Turkish Coffee Finally, Multi-Step Synthesis, and AI as Enhancement

Chris Gmyr and TJ Miller talk about the long-awaited Turkish coffee...

010

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 20/05/2026

A 10-day feature is usually 1 day of typing and 9 days of waiting. Code review queue, env provisioning, approval chains, deploy windows, staging access. #AI sped up the 1 day. The 9 days didn't move. That's the speed problem nobody's solving.

151

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 19/05/2026

A green test run tells you nothing about whether the system works. Especially when #AI rewrites the implementation and the test suite in the same change. What you're measuring now is whether the model kept both sides consistent. That's not correctness. That's just internal agreement.

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 18/05/2026

Two lines a day in your work log. What shipped, who you influenced. That's the brag doc that survives manager changes. New Dev Notes 👇 chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: May 18, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

031

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 15/05/2026

💡 Managers change. Leadership changes too. A brag doc stays with you and survives all management changes and shifts. New leadership can read what you did. Old leadership won't remember. It's not ego work, it's continuity work

031

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 14/05/2026

Code golf is dead. The whole game was "fewer characters wins." #AI handles the typing now. The new game is "will a stranger understand this in six months." Verbose and clear beats terse and clever. Optimize for the human reading the diff, not the one writing it 💡

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 13/05/2026

Claude's first answer is rarely its best one. The second pass usually beats it. The third sometimes beats the second. Stop accepting the first response as the answer. Push back, ask for alternatives, or just say "try again." The cost is one more turn. The value is real #ai

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 12/05/2026

Rolled Claude rules, Copilot config, and a baseline CLAUDE md to 30+ repos with one repeatable workflow. Teams reviewed and merged their own. The work per repo collapses to about a day once settled. You can move tooling fast across an org as long as adoption stays a team decision

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 11/05/2026

Comprehension is the job. #AI just moved where the work lives. First Monday issue of Dev Notes chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: May 11, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 08/05/2026

Heads up: Dev Notes moves to Monday mornings starting 5/11. Same format, new slot. Sign up if you want a weekly developer newsletter to kick off your week - I'd love to have you 🚀 chrisgmyr.dev/newsletter

chrisgmyr.dev

Dev Notes Newsletter - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 17/04/2026

New Dev Notes 📬 Most engineers treat #AI output as a single answer: prompt, read, copy, move on. The real skill is closing the loop. Wrote about iterating with the agent, rewinding bad branches, and the two skills I built this week to force it chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: April 17, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 15/04/2026

Every time Claude Code does something unexpected, pause and ask it to reflect on the gap. Have it propose a change to your skills, rules, or config. Push it and move on. We're shipping 1-3 harness improvements a day without stopping feature work. The #AI setup improves as a side effect of using it 🚀

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 14/04/2026

The biggest blocker to #AI adoption isn't the tooling. It's confidence. Watched an engineer hesitate to use AI on a shared repo because they weren't sure the output would hold up in review. The tools are ready. The trust isn't. That gap closes with pairing, not mandates 🧠

011

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 13/04/2026

Most people stuff everything into CLAUDE.md because they're afraid the model will miss something. It grows until the model ignores half of it. The fix is the opposite: load only what's relevant to the current task - trust that less context with higher signal beats more context with more noise 🧠 #ai

011

Slightly Caffeinated Podcast @slightlycaffeinated.fm · 11/04/2026

🎙️ Just published a new episode of Slightly Caffeinated: Still No Turkish Coffee, Audit Pipelines, and ButcherBox Automation. Have a listen:

share.transistor.fm

Still No Turkish Coffee, Audit Pipelines, and ButcherBox Automation

TJ Miller and Chris Gmyr discuss their recent projects involving AI,...

000

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 09/04/2026

💡 Ran an #AI office hours session this week. The biggest takeaway wasn't a workflow or a tool. It was that nobody is far ahead on this. The field is too new for best practices. If you're experimenting at all, you're in the top quartile. Lower your threshold for sharing what you learn

021

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 08/04/2026

Model weights don't change between sessions. If it makes the same mistake twice, that's not the model's fault. That's a missing rule. Encode the fix in your repo and it never happens again. Prompt engineering is debugging, not conversation #ai

121

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 07/04/2026

CLAUDE.md and MEMORY.md have hard limits on what they can hold. Most people treat that as a constraint. I think it's a design signal: if your agent needs more context than fits in a static file, you need conditional loading, not a bigger file. Hooks and rules beat a giant instruction doc every time.

131

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 31/03/2026

🚀 New blog post: "My #AI Agent Knows What Project I’m Working On Before I Tell It." I got tired of loading the same context files every session. I built a hook that reads my first message and loads the right project automatically. Bit of bash, JSON config, and zero AI inference 👇🏻

342

Reposted by Slightly Caffeinated Podcast

Chris Gmyr @chrisgmyr.dev · 27/03/2026

New Dev Notes 📬 I've been building startup hooks, context files, and keyword-matching scripts in Claude Code. I read a "Harness Engineering" article and now have a better name for it. Wrote about what that looks like in practice and why most teams haven't started chrisgmyr.dev/newsletter/d...

chrisgmyr.dev

Dev Notes: March 27, 2026 - Dev Notes - Chris Gmyr

Staff Software Engineer at Rula. Newsletter author, podcast co-host, and builder of things.

251

Slightly Caffeinated Podcast @slightlycaffeinated.fm · 14/03/2026

🎙️ Just published a new episode of Slightly Caffeinated: New Adventures, Iris Long Running Jobs, and Multi-Threaded Conversations. Have a listen:

share.transistor.fm

New Adventures, Iris Long Running Jobs, and Multi-Threaded Conversations

TJ Miller and Chris Gmyr share updates on their personal projects,...

010